This message was deleted.

this will depend on your dataset and model. I like to run an experiment without, or at least very little, transformations first

any recommendation to some transformations if you deal with this before?

which model are you using

i am trying different models neural forecast and mlforecast

Hi @marah othman. You dont need to normalize the data before send it to the models. The models of both libraries have inbuilt scalers that take care of the normalization. For

neuralforecast

, you only need to specify the

scaler_type

in the initialization of the model (the recommended scalers are

robust

and

minmax1

that nice thank you